INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     JSON
    0.46
    0.46
    JSON
    0.45
     phasor
    0.44
     unimplemented
    0.41
     PLIST
    0.41
     consents
    0.40
     polynom
    0.40
    NaBH
    0.40
     plist
    0.40
    POSITIVE LOGITS
     footwear
    2.64
     shoes
    2.61
    2.45
     shoe
    2.38
     sandals
    2.33
    2.27
     Shoes
    2.25
    Shoes
    2.22
     chaussures
    2.16
     sepatu
    2.14
    Act Density 0.092%

    No Known Activations